For a study sponsored by the National Institute of Justice, data scientists applied “machine-learning techniques” to look at nearly two decades’ worth of police reports on rape cases. They found that, in rape cases, officers’ subjective conclusions and opinions, and how they are worded in written reports, may affect key procedural decisions down the line, such as whether to prosecute a rape case.
Those who read reports, the study found, can be “signaled” about the worthiness of a case when they read derisive descriptions of victims such as this one: (officer) “. . . observed no bruises, contusions on the female nor were her clothes disheveled. At times during the interview, she smirked as if it was funny, but she did show signs that she was in pain or discomfort.”
In the end, the study recommends that law-enforcement agencies should prioritize improved report writing and that officers investigating rape cases should include a narrative provided by the victim that conveys the trauma of rape. Also, researchers emphasized that reports should document as many details about the rape as possible, such as the victim’s fears and thoughts and what they heard, saw, smelled, and tasted.
The study — conducted by a team of scholars from Case Western University, Cleveland State University, and Texas A&M University — aimed to identify linguistic “signaling” of officers’ views or biases found in their narratives of rape reports. The research team evaluated narratives in more than 5,600 police reports of rape in a large urban jurisdiction from 1993–2011.
Overall, the reports did not contain high levels of sentiment. But the study found that longer, more detailed police reports were highly predictive of more investigative activity and successful case outcomes such as convictions and that the rape cases with the most successful prosecution outcomes tended to have significant positive officer sentiment and subjectivity in the police incident reports compared to reports with negative or neutral (non-significant) officer sentiment. Researchers found that Black victims tended to be subjects of police reports with fewer words and with words that were more negative or subjective compared to reports on non-Black victims, almost all of whom were white.